Commit Graph
2 Commits
Author SHA1 Message Date
SijiaYang cb9d91ea8a feat: support DeepSeek-R1-W4AFP8 model with ep-moe mode (#7762)
Signed-off-by: yangsijia.614 <yangsijia.614@bytedance.com>
2025-07-07 14:47:21 -07:00
SijiaYangandyicwang da3890e82a [1/n]: add cutlass W4A8 moe kernel for hopper architecture (#7772)
Signed-off-by: yangsijia.614 <yangsijia.614@bytedance.com>
Co-authored-by: yicwang <yichen.wang@bytedance.com>
2025-07-04 20:50:12 -07:00